Logo
For AI Agents

Give your AI agent hands and eyes on every PDF

Every open, dwell, annotation and form fill on your documents — typed, attributed to a named reader, and ready for your agent to query and act on. Over MCP, REST and webhooks. Apdf is the PDF engagement layer for apps and agents.

Free plan, no card OAuth 2.0 MCP endpoint EU-hosted by default
agent · deal-desk connected to apdf
Who read the Acme proposal past pricing — and who stalled?
called apdf.list-documents
called apdf.get-document-analytics
called apdf.get-document-session
Three of five reached pricing. Alex returned twice and highlighted the monthly rate — drafting the follow-up now.
then Follow-up drafted CRM updated

Most PDF tools for agents
stop at the file.

Reader MCPs tell your agent what's inside a document. Generator APIs render one and hang up. Neither knows what happens after you hit send — and that's where the deal lives.

Reader MCPs

Read the file

Extract text, parse tables, OCR a scan. Useful — but the story ends at the last page. What a human did with the document never becomes data.

Generator APIs

Render and forget

HTML in, PDF out. The moment the file is delivered, the API's job is done. Whether anyone opened it, read it or walked away — silence.

Apdf

Close the loop

Your agent builds the PDF, shares it to a named reader, watches every move as typed events — and acts on what it sees. Make → share → watch → act, one endpoint.

You own the signal. We host the surface. MCP is one of three rails — the same data flows over REST and webhooks.

The toolset

PDF MCP tools for the whole engagement loop.

Every tool below is live on the MCP endpoint and mirrored in the REST API. Names map one-to-one — what your agent calls in chat, your backend can call in code.

Share

PDF tracking links for AI agents

The agent publishes a document and mints a tokenized link per recipient — no reader logins, identity embedded in every event that follows. Links activate, deactivate and revoke on command, even mid-read.

create-document list-documents get-document archive-document unarchive-document make-document-public make-document-private delete-document create-document-link list-document-links activate-document-link deactivate-document-link delete-document-link
Measure

PDF engagement analytics for AI agents

Who opened, which page held their attention and for how long, who returned, where they dropped off — plus every annotation and form submission as structured, attributed data. The agent asks; the answer is already typed.

get-document-analytics list-document-sessions get-document-session list-document-annotations list-document-form-submissions
Watch

Automation & job monitoring for agents

The agent inspects your when/filter/then rules and their full execution log — payload, response, duration per firing — and checks on long-running PDF jobs without polling blind.

list-automations list-automation-executions check-job-status
Make

PDF generation & processing for AI agents

The engagement layer sits on a full PDF engine, so the agent can also build the document it's about to track — generate from HTML, merge, split, compress, OCR, watermark, secure — without a second vendor.

create-pdf-file merge-pdf-files split-pdf-file compress-pdf-file convert-pdf-to-image extract-pdf-pages delete-pdf-pages rotate-pdf-pages overlay-pdf-pages underlay-pdf-pages read-pdf-content search-pdf-content read-pdf-metadata convert-pdf-with-ocr read-pdf-content-with-ocr search-pdf-content-with-ocr add-pdf-security remove-pdf-security

Wakes on the signal.
Acts while it's hot.

Chat is the demo. The production shape is event-driven: reader signals wake your agent, MCP gives it context and hands, and the follow-up happens while the document is still open.

01

A reader moves

Alex leaves the pricing page after a long dwell. The motion lands as a typed event, attributed to the recipient link.

page:leave · pricing · 1m 12s
02

The signal wakes your agent

A when/filter/then automation matches the event and POSTs the payload to your agent's endpoint. No polling, no cron.

webhook → your agent
03

It pulls the context

Over MCP, the agent reads the full session: pages, dwell, return visits, the annotation on the rate line.

get-document-session
04

It acts while interest is hot

A follow-up drafted around the exact objection, the CRM stage moved, a fresh link minted for the CFO.

create-document-link
In practice

Playbooks your agent can run on day one.

Each card is a workflow an agent runs end to end — from Claude, Cursor, a framework of your own, or headless against the REST API.

The proposal chaser

Every morning the agent sweeps active proposals, ranks readers by real attention instead of opens, and flags exactly where each stalled reader stopped.

prompt
“Which proposals stalled this week, and where did each reader stop?”
calls list-documents get-document-analytics list-document-sessions

The objection triager

A reader highlights a line and leaves a comment. The agent wakes, reads the exact quote in context, files the objection in the CRM and pings the deal owner.

wakes on
annotation:create
calls list-document-annotations get-document-session

The intake processor

Vendor intake runs through PDF forms. On every submission the agent checks the typed field data for completeness, files it, and issues a confirmation document.

wakes on
form:submit
calls list-document-form-submissions create-pdf-file create-document-link

The deal-desk factory

One instruction builds the proposal from your HTML template, publishes it as a tracked document, and mints a personalized link for every stakeholder on the deal.

prompt
“Build the Contoso proposal from this draft and send each stakeholder their own link.”
calls create-pdf-file create-document create-document-link

Connect once.
Bring any client.

One OAuth-signed MCP endpoint for chat clients and agent frameworks — and the same tools over REST for everything that doesn't speak MCP yet.

MCP

Sign in from your client

apdf.io/mcp/main
OAuth 2.0 · no API keys, no token files
Claude
Claude
ChatGPT
ChatGPT
Cursor
Cursor
Gemini
Gemini
REST

Or call it like an API

$ curl https://apdf.io/api/documents/{docId}/analytics \
-H "Authorization: Bearer YOUR_API_TOKEN"

Every MCP tool has a REST twin, and webhooks push events the moment they happen — so headless agents, cron jobs and your own product all drink from the same stream.

API reference
Trust

Autonomy, with guardrails.

An agent acting on live reader data needs boundaries you can see and pull. They're built in, not bolted on.

OAuth-scoped access

Agents sign in over OAuth 2.0 and get exactly the workspace access you grant — revoke a connection and the tools go dark.

Revocable mid-read

Every recipient link can be deactivated at any moment — by you, or by an agent that spots something off.

A full audit trail

Every automation firing is logged with payload, response and duration. What acted, when, and on what signal — always answerable.

EU-hosted, GDPR-native

Documents and engagement data live on EU infrastructure by default.

Never training data

Your documents and your readers' behavior are never used to train models. Period.

No lock-in

Full data export on demand, an open API underneath everything. Leave whenever — with everything.

Quick check

All these questions
have the same answer.

Yes.
And the nuanced ones, answered straight

MCP access comes with the paid plans — and every new account starts with a 14-day Pro trial, no card required, so you can connect your agent on day one. The REST API is available on every plan, including the free one.

No — and that's the point. Each recipient gets a tokenized link, so every event your agent sees arrives already attributed to a name and email. No reader sign-ups, no exports, no CRM joins.

EU-hosted by default and GDPR-native. Your documents and reader events are never used as training data, and you can export everything on demand.

Not at all. MCP is one of three delivery rails: the full toolset is mirrored in the REST API, and webhooks push every event as it happens. Anything that can make an HTTP request can run the same playbooks.

Own the signal.
Arm the agent.